© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31433
    Prev
    Next
    INDEX
    Explanations

    partial derivative, integral formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĺ±
    -0.07
    aire
    -0.07
    rib
    -0.07
    atat
    -0.07
    तà¥įया
    -0.06
    ilar
    -0.06
    OTS
    -0.06
     arbitrary
    -0.06
    ELLO
    -0.06
    /tab
    -0.06
    POSITIVE LOGITS
    æµ®äºij
    0.10
    ewolf
    0.08
    alfa
    0.08
    çĪ¶
    0.08
    rel
    0.07
     иÑģÑĤо
    0.07
    å°±æĺ¯ä½ł
    0.07
    foy
    0.07
    GetSize
    0.07
    为群ä¼Ĺ
    0.07
    Activations Density 0.027%

    No Known Activations